Gemini 2.0 Pro Experimental

Gemini 1.5 Pro

Gemini 1.5 Pro handles infinite context with 99% retrieval accuracy at 750k tokens via Mixture-of-Experts and generates chapter summaries for 2-hour videos with 92% accuracy.

Gemini 2.5 Pro Experimental

Gemini 2.5 Pro Experimental is Google's advanced model with improved multimodal reasoning, long context understanding with 1 million tokens, and specialized video comprehension.

Gemini 2.0 Flash Thinking

Gemini 2.0 Flash Thinking offers subsecond reasoning with 840 ms median response time for financial forecasting and an energy-efficient architecture using 0.8 kWh per million tokens (40% less than Gemini 1.5).

Gemini 2.5 Flash Preview

Google's state-of-the-art workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. Features hybrid reasoning (thinking on/off) with configurable budgets, balancing quality, cost, and latency.

Gemini 2.5 Flash Preview (thinking)

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

PaLM 2 Chat

PaLM 2 by Google features improved multilingual, reasoning, and coding capabilities. Optimized for chat-based interactions.

Gemini Pro 1.0

Google's flagship multimodal model (as of release). Designed for natural language tasks, multi-turn chat, code generation, and understanding image inputs.

Gemini 2.5 Pro (I/O Edition)

Our most advanced reasoning model, capable of solving complex problems. Best for multimodal understanding, reasoning over complex problems, complex prompts, tackling multi-step code, math and STEM problems, coding (especially web development), and analyzing large datasets/codebases/documents with long context. Knowledge cutoff Jan 2025.